def log()

in trl/trainer/grpo_trainer.py [0:0]

• 31 lines of code
• 13 McCabe index (conditional complexity)

    def log(self, logs: dict[str, float], start_time: Optional[float] = None) -> None:
        mode = "train" if self.model.training else "eval"
        metrics = {key: sum(val) / len(val) for key, val in self._metrics[mode].items()}  # average the metrics

        # This method can be called both in training and evaluation. When called in evaluation, the keys in `logs`
        # start with "eval_". We need to add the prefix "eval_" to the keys in `metrics` to match the format.
        if mode == "eval":
            metrics = {f"eval_{key}": val for key, val in metrics.items()}

        logs = {**logs, **metrics}
        super().log(logs, start_time)
        self._metrics[mode].clear()

        if self.accelerator.is_main_process and self.log_completions:
            if is_rich_available():
                print_prompt_completions_sample(
                    self._textual_logs["prompt"],
                    self._textual_logs["completion"],
                    self._textual_logs["rewards"],
                    self._textual_logs["advantages"],
                    self.state.global_step,
                    self.num_completions_to_print,
                )

            if self.args.report_to and "wandb" in self.args.report_to and wandb.run is not None:
                import pandas as pd

                table = {
                    "step": [str(self.state.global_step)] * len(self._textual_logs["prompt"]),
                    "prompt": self._textual_logs["prompt"],
                    "completion": self._textual_logs["completion"],
                    **self._textual_logs["rewards"],
                    "advantage": self._textual_logs["advantages"],
                }
                df = pd.DataFrame(table)
                if self.wandb_log_unique_prompts:
                    df = df.drop_duplicates(subset=["prompt"])
                wandb.log({"completions": wandb.Table(dataframe=df)})